Convolutional neural networks (CNNs) have become an established part of numerous safety-critical computer vision applications, including human robot interactions and automated driving. Real-world implementations will need to guarantee their robustness against hardware soft errors corrupting the underlying platform memory. Based on the previously observed efficacy of activation clipping techniques, we build a prototypical safety case for classifier CNNs by demonstrating that range supervision represents a highly reliable fault detector and mitigator with respect to relevant bit flips, adopting an eight-exponent floating point data representation. We further explore novel, non-uniform range restriction methods that effectively suppress the probability of silent data corruptions and uncorrectable errors. As a safety-relevant end-to-end use case, we showcase the benefit of our approach in a vehicle classification scenario, using ResNet-50 and the traffic camera data set MIOVision. The quantitative evidence provided in this work can be leveraged to inspire further and possibly more complex CNN safety arguments.
Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Institute of Control Engineering（北京控制工程研究所）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）
Winograd Convolution: A Perspective from Fault Tolerance
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）
Adversarial Examples as an Input-Fault Tolerance Problem
University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；University of Waterloo（滑铁卢大学）；Perimeter Institute for Theoretical Physics（圆周理论物理研究所）
Fault Tolerance of Neural Networks in Adversarial Settings
Indraprastha Institute of Information Technology（英迪拉普拉斯信息技术研究所）；Scientific Analysis Group（科学分析小组）；Institute for Systems Studies and Analyses（系统研究与分析研究所）；Aurel Vlaicu University of Arad（阿拉德奥雷尔弗拉伊库大学）
Towards Fault Tolerance in Multi-Agent Reinforcement Learning
Tsinghua University（清华大学）；QiYuan Lab（启元实验室）；Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University（北京信息科学与技术国家研究中心（BNRist），清华大学）
Improving DNN Fault Tolerance using Weight Pruning and Differential Crossbar Mapping for ReRAM-based Edge AI
Northeastern University（东北大学）；North Dakota State University（北达科他州立大学）；Washington State University（华盛顿州立大学）；University of Connecticut（康涅狄格大学）；Chongqing University（重庆大学）；University of South Alabama（南阿拉巴马大学）
Towards Enhancing Fault Tolerance in Neural Networks
University of Waterloo（滑铁卢大学）；Indraprastha Institute of Information Technology (IIIT), Delhi（德里英德拉普拉斯塔信息技术学院）；Institute for Systems Studies & Analyses（系统研究与分析所）；Aurel Vlaicu University of Arad（阿拉德奥雷尔·弗拉伊库大学）
